# Linking Surface Facts to Large-Scale Knowledge Graphs

arXiv: https://arxiv.org/abs/2310.14909 · HTML: https://mlsanity.com/paper/2310.14909/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 74 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [PyTorch-BigGraph: A Large-scale Graph Embedding System](https://mlsanity.com/paper/1903.12287/) (2019)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [Inductive Entity Representations from Text via Link Prediction](https://mlsanity.com/paper/2010.03496/) (2020)
- [Multi-Dimensional Evaluation of Text Summarization with In-Context Learning](https://mlsanity.com/paper/2306.01200/) (2023)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)
- [CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information](https://mlsanity.com/paper/1902.00172/) (2019)
- [Multi2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT](https://mlsanity.com/paper/2009.08128/) (2020)
- [Towards More Fine-grained and Reliable NLP Performance Prediction](https://mlsanity.com/paper/2102.05486/) (2021)
- [Falcon 2.0: An Entity and Relation Linking Tool over Wikidata](https://mlsanity.com/paper/1912.11270/) (2019)
- [OPIEC: An Open Information Extraction Corpus](https://mlsanity.com/paper/1904.12324/) (2019)
- [SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2210.04870/) (2022)
- [Conversational Entity Linking: Problem Definition and Datasets](https://mlsanity.com/paper/2105.04903/) (2021)
- [BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation](https://mlsanity.com/paper/2109.06850/) (2021)
- [OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference](https://mlsanity.com/paper/1904.12606/) (2019)
- [Human-Centric Research for NLP: Towards a Definition and Guiding Questions](https://mlsanity.com/paper/2207.04447/) (2022)

## Built on by (most cited first, 5 of 5)

- [Patient-Centric Knowledge Graphs: A Survey of Current Methods, Challenges, and Applications](https://mlsanity.com/paper/2402.12608/) (2024)
- [On Synthesizing Data for Context Attribution in Question Answering](https://mlsanity.com/paper/2504.05317/) (2025)
- [Supervised In-Context Fine-Tuning for Generative Sequence Labeling](https://mlsanity.com/paper/2509.00921/) (2025)
- [TextMineX: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action](https://mlsanity.com/paper/2509.15098/) (2025)
- [From Symbolic to Natural-Language Relations: Rethinking Knowledge Graph Construction in the Era of Large Language Models](https://mlsanity.com/paper/2601.09069/) (2026)

## Abstract (arXiv)

Open Information Extraction (OIE) methods extract facts from natural language text in the form of ("subject"; "relation"; "object") triples. These facts are, however, merely surface forms, the ambiguity of which impedes their downstream usage; e.g., the surface phrase "Michael Jordan" may refer to either the former basketball player or the university professor. Knowledge Graphs (KGs), on the other hand, contain facts in a canonical (i.e., unambiguous) form, but their coverage is limited by a static schema (i.e., a fixed set of entities and predicates). To bridge this gap, we need the best of both worlds: (i) high coverage of free-text OIEs, and (ii) semantic precision (i.e., monosemy) of KGs. In order to achieve this goal, we propose a new benchmark with novel evaluation protocols that can, for example, measure fact linking performance on a granular triple slot level, while also measuring if a system has the ability to recognize that a surface form has no match in the existing KG. Our extensive evaluation of several baselines show that detection of out-of-KG entities and predicates is more difficult than accurate linking to existing ones, thus calling for more research efforts on this difficult task. We publicly release all resources (data, benchmark and code) on https://github.com/nec-research/fact-linking.